Generative AI - Text to Video

AI generate video and audio from text prompts.

How to install

Download the add-on: https://github.com/tin2tin/text_to_video/archive/refs/heads/main.zip

Run Blender as Administrator and install the add-on as usual: Preferences > Add-ons > Install > select file > Enable the add-on.

Now, in the add-on preferences, hit the "Install all Dependencies" button, and many GB will have to be downloaded, so go grab a coffee.

Weights

Pruned 6 GB VRAM(included in the add-on download):

https://huggingface.co/kabachuha/modelscope-damo-text2video-pruned-weights/tree/main

20 GB of VRAM:

https://modelscope.cn/models/damo/text-to-video-synthesis/files

Anime - 6 GB VRAM:

https://huggingface.co/kabachuha/animov-0.1-modelscope-original-format

Location

Video Sequence Editor > Sidebar > Generative AI

Notification sound can be changed or switched on/off under Preferences:

Converting Text strips into GeneratorAI strips:

How to

In order to make Blender run the generated video properly, the resolution and the fps should be set to match the footage. The resolution can be set by selecting a strip > Strip Menu > Movie Strip > Set Render Size. The project/scene fps can be set in the Properties > Output Tab > Format > Frame Rate - set it to Custom and 8.

Alternatively can this .blend be loaded as a quick start, but the add-on still needs to be installed:

https://github.com/tin2tin/text_to_video/raw/main/text2video_ui.blend

Text to Audio

Find documentation here: https://github.com/haoheliu/AudioLDM

Issue: https://github.com/huggingface/diffusers/issues/3091

Modules

Diffusers: https://github.com/huggingface/diffusers

ModelScope: https://modelscope.cn/models/damo/text-to-video-synthesis/summary

AudioLDM: https://github.com/haoheliu/AudioLDM

If some additional python modules are missing, write about it here(so I can add them), and use the Blender PIP add-on to manually install the missing modules:

https://github.com/amb/blender_pip